DocumentCode :
2408302
Title :
Exploiting segmentation for robust 3D object matching
Author :
Krainin, Michael ; Konolige, Kurt ; Fox, D.
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA
fYear :
2012
fDate :
14-18 May 2012
Firstpage :
4399
Lastpage :
4405
Abstract :
While Iterative Closest Point (ICP) algorithms have been successful at aligning 3D point clouds, they do not take into account constraints arising from sensor viewpoints. More recent beam-based models take into account sensor noise and viewpoint, but problems still remain. In particular, good optimization strategies are still lacking for the beam-based model. In situations of occlusion and clutter, both beam-based and ICP approaches can fail to find good solutions. In this paper, we present both an optimization method for beambased models and a novel framework for modeling observation dependencies in beam-based models using over-segmentations. This technique enables reasoning about object extents and works well in heavy clutter. We also make available a ground-truth 3D dataset for testing algorithms in this area.
Keywords :
image matching; image segmentation; inference mechanisms; iterative methods; optimisation; solid modelling; 3D point clouds; ICP approach; beam-based models; ground-truth 3D dataset; iterative closest point algorithms; object extent reasoning; optimization method; over-segmentations; robust 3D object matching; segmentation exploitation; sensor noise; sensor viewpoints; Clutter; Computational modeling; Data models; Estimation; Iterative closest point algorithm; Optimization; Robot sensing systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation (ICRA), 2012 IEEE International Conference on
Conference_Location :
Saint Paul, MN
ISSN :
1050-4729
Print_ISBN :
978-1-4673-1403-9
Electronic_ISBN :
1050-4729
Type :
conf
DOI :
10.1109/ICRA.2012.6224714
Filename :
6224714
Link To Document :
بازگشت